Non-Intrusive Load Monitoring Method for Multi-Energy Coupling Appliances Considering Spatio-Temporal Coupling

The multi-energy coupling (MEC) appliances couple electricity, gas, heat, and cold, of which the gas, heat, and cold have long transient processes. However, these transient features have never been considered in past non-intrusive load monitoring (NILM) methods. This paper proposes a novel NILM method for MEC appliances considering spatio-temporal coupling, which combines semi-supervised learning and weakly supervised learning. Firstly, the unlabeled historical events are labeled by graph-based semi-supervised learning (GBSSL) and distinguished into three categories, i.e., reliable, uncertain, and unreliable samples. Then, to fully use of spatio-temporal coupling information, the unreliable samples are discarded and the feature vectors of other samples are expanded into spatio-temporal coupling feature vectors. To improve the accuracy of load identification, this paper proposes a two-stage deep learning framework “Teaching and Mutual Learning” (TML). In the teaching stage, two convolutional neural networks (CNN) are pre-trained with reliable samples. In the mutual learning stage, the noise samples are filtered by using the different learning abilities of the two networks. The effectiveness and superiority of the proposed method are verified on five types of MEC appliances in a park IES.